scholarly journals Deep Learning-Based Transfer Learning for Classification of Skin Cancer

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 8142
Author(s):  
Satin Jain ◽  
Udit Singhania ◽  
Balakrushna Tripathy ◽  
Emad Abouel Nasr ◽  
Mohamed K. Aboudaif ◽  
...  
Keyword(s):  
Skin Cancer ◽  
Transfer Learning ◽  
Skin Color ◽  
Human Society ◽  
False Negatives ◽  
Low Frequencies ◽  
Major Health ◽  
Automated Tools ◽  
Made In

One of the major health concerns for human society is skin cancer. When the pigments producing skin color turn carcinogenic, this disease gets contracted. A skin cancer diagnosis is a challenging process for dermatologists as many skin cancer pigments may appear similar in appearance. Hence, early detection of lesions (which form the base of skin cancer) is definitely critical and useful to completely cure the patients suffering from skin cancer. Significant progress has been made in developing automated tools for the diagnosis of skin cancer to assist dermatologists. The worldwide acceptance of artificial intelligence-supported tools has permitted usage of the enormous collection of images of lesions and benevolent sores approved by histopathology. This paper performs a comparative analysis of six different transfer learning nets for multi-class skin cancer classification by taking the HAM10000 dataset. We used replication of images of classes with low frequencies to counter the imbalance in the dataset. The transfer learning nets that were used in the analysis were VGG19, InceptionV3, InceptionResNetV2, ResNet50, Xception, and MobileNet. Results demonstrate that replication is suitable for this task, achieving high classification accuracies and F-measures with lower false negatives. It is inferred that Xception Net outperforms the rest of the transfer learning nets used for the study, with an accuracy of 90.48. It also has the highest recall, precision, and F-Measure values.

scholarly journals TO THE QUESTION OF IMPORTANCE OF DEVELOPMENT OF THE HUMANITARIAN SPHERE IN THE CONDITIONS OF MODERN TECHNOLOGICAL PROGRESS

2020 ◽  
pp. 33-36
Author(s):  
Е. В. Яковлева
Keyword(s):  
Spiritual Development ◽  
Social System ◽  
Technological Progress ◽  
Technological Development ◽  
Human Society ◽  
Modern Level ◽  
Scientific Ethics ◽  
Made In

В статье рассматриваются проблемы, связанные с современным уровнем развития науки и техники. Ставится вопрос о рисках, связанных с интенсивным технологическим развитием человеческого общества. Рассматриваются экологический, социальный, геополитический уровни приложения проблемы. Анализируется концепция Э. Фромма о балансе между техническим и духовным развитием, рассматривается теория А. П. Назаретяна о техно-гуманитарном балансе как условии выживания социальной системы. На основании проведенной в статье классификации исследовательских подходов оценивается роль современных исследований в области научной этики в разрешении проблемы и делается вывод о необходимости выхода на уровень практического ее разрешения. Consideration of the problems connected with the modern level of development of science and technology is made in the article. The question of the risks connected with intensive technological development of human society is raised. Ecological, social, geopolitical aspects of a problem are considered. Fromm’s concept about balance between technical and spiritual development is analyzed, A. P. Nazaretyan’s theory about technical and humanitarian balance as a condition of survival of social system is considered. On the basis of the classification of research approaches which is carried out in article the role of modern researches in the field of scientific ethics in solution of the problem is estimated and the conclusion about need of an exit to the level of her practical permission is drawn.

Deep Learning-Based Classification of Malignant and Benign Cells in Dermatoscopic Images via Transfer Learning Approach

2021 ◽  
Author(s):  
V. Akash Kumar ◽  
Vijaya Mishra ◽  
Monika Arora
Keyword(s):  
Skin Cancer ◽  
Transfer Learning ◽  
Human Life ◽  
Skin Pigmentation ◽  
Automatic Identification ◽  
Learning Approach ◽  
Predicted Model ◽  
Classification Tasks ◽  
Cancerous Cells

The inhibition of healthy cells creating improper controlling process of the human body system indicates the occurrence of growth of cancerous cells. The cluster of such cells leads to the development of tumor. The observation of this type of abnormal skin pigmentation is done using an effective tool called Dermoscopy. However, these dermatoscopic images possess a great challenge for diagnosis. Considering the characteristics of dermatoscopic images, transfer learning is an appropriate approach of automatically classifying the images based on the respective categories. An automatic identification of skin cancer not only saves human life but also helps in detecting its growth at an earlier stage which saves medical practitioner’s effort and time. A newly predicted model has been proposed for classifying the skin cancer as benign or malignant by DCNN with transfer learning and its pre-trained models such as VGG 16, VGG 19, ResNet 50, ResNet 101, and Inception V3. The proposed methodology aims at examining the efficiency of pre-trained models and transfer learning approach for the classification tasks and opens new dimensions of research in the field of medicines using imaging technique which can be implementable in real-time applications.

Classification of Skin Cancer Lesions Using Deep Neural Networks and Transfer Learning

2021 ◽  
pp. 259-268
Author(s):  
Danny Joel Devarapalli ◽  
Venkata Sai Dheeraj Mavilla ◽  
Sai Prashanth Reddy Karri ◽  
Harshit Gorijavolu ◽  
Sri Anjaneya Nimmakuri
Keyword(s):  
Neural Networks ◽  
Skin Cancer ◽  
Transfer Learning ◽  
Deep Neural Networks

scholarly journals Acral melanoma detection using dermoscopic images and convolutional neural networks

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Qaiser Abbas ◽  
Farheen Ramzan ◽  
Muhammad Usman Ghani
Keyword(s):  
Deep Learning ◽  
Skin Cancer ◽  
Transfer Learning ◽  
Clinical Decision Making ◽  
Data Augmentation ◽  
Automated System ◽  
Convolutional Network ◽  
Acral Melanoma ◽  
Melanoma Subtypes

AbstractAcral melanoma (AM) is a rare and lethal type of skin cancer. It can be diagnosed by expert dermatologists, using dermoscopic imaging. It is challenging for dermatologists to diagnose melanoma because of the very minor differences between melanoma and non-melanoma cancers. Most of the research on skin cancer diagnosis is related to the binary classification of lesions into melanoma and non-melanoma. However, to date, limited research has been conducted on the classification of melanoma subtypes. The current study investigated the effectiveness of dermoscopy and deep learning in classifying melanoma subtypes, such as, AM. In this study, we present a novel deep learning model, developed to classify skin cancer. We utilized a dermoscopic image dataset from the Yonsei University Health System South Korea for the classification of skin lesions. Various image processing and data augmentation techniques have been applied to develop a robust automated system for AM detection. Our custom-built model is a seven-layered deep convolutional network that was trained from scratch. Additionally, transfer learning was utilized to compare the performance of our model, where AlexNet and ResNet-18 were modified, fine-tuned, and trained on the same dataset. We achieved improved results from our proposed model with an accuracy of more than 90 % for AM and benign nevus, respectively. Additionally, using the transfer learning approach, we achieved an average accuracy of nearly 97 %, which is comparable to that of state-of-the-art methods. From our analysis and results, we found that our model performed well and was able to effectively classify skin cancer. Our results show that the proposed system can be used by dermatologists in the clinical decision-making process for the early diagnosis of AM.

scholarly journals Big transfer learning for automated skin cancer classification

2021 ◽  
Vol 23 (3) ◽  
pp. 1611
Author(s):  
Zinah Mohsin Arkah ◽  
Dalya S. Al-Dulaimi ◽  
Ahlam R. Khekan
Keyword(s):  
Deep Learning ◽  
Skin Cancer ◽  
Transfer Learning ◽  
Image Features ◽  
Cancer Classification ◽  
Automated Classification ◽  
Novel Approach ◽  
Learned Features ◽  
Manual Classification

<p>Skin cancer is an example of the most dangerous disease. Early diagnosis of skin cancer can save many people’s lives. Manual classification methods are time-consuming and costly. Deep learning has been proposed for the automated classification of skin cancer. Although deep learning showed impressive performance in several medical imaging tasks, it requires a big number of images to achieve a good performance. The skin cancer classification task suffers from providing deep learning with sufficient data due to the expensive annotation process and required experts. One of the most used solutions is transfer learning of pre-trained models of the ImageNet dataset. However, the learned features of pre-trained models are different from skin cancer image features. To end this, we introduce a novel approach of transfer learning by training the pre-trained models of the ImageNet (VGG, GoogleNet, and ResNet50) on a large number of unlabelled skin cancer images, first. We then train them on a small number of labeled skin images. Our experimental results proved that the proposed method is efficient by achieving an accuracy of 84% with ResNet50 when directly trained with a small number of labeled skin and 93.7% when trained with the proposed approach.</p>

ASPECTS IN BUILDING A COMPANY WEB-SITE AND ITS ROLE FOR THE DEVELOPMENT OF BUSINESS

2018 ◽  
pp. 117-124
Author(s):  
Petar Halachev ◽  
Victoria Radeva ◽  
Albena Nikiforova ◽  
Miglena Veneva
Keyword(s):  
Life Cycle ◽  
Web Site ◽  
The Internet ◽  
A Company ◽  
The Web ◽  
Design Construction ◽  
Made In ◽  
Site Types

This report is dedicated to the role of the web site as an important tool for presenting business on the Internet. Classification of site types has been made in terms of their application in the business and the types of structures in their construction. The Models of the Life Cycle for designing business websites are analyzed and are outlined their strengths and weaknesses. The stages in the design, construction, commissioning, and maintenance of a business website are distinguished and the activities and requirements of each stage are specified.

Vegetation on technogenic habitats in the far-north taiga and south forest-tundra of the European North-East of Russia. Alliance Chamerio angustifolii–Matricarion hookeri A. Ishbirdin et al. 1996

2019 ◽  
pp. 77-94
Author(s):  
I. A. Likhanova ◽  
G. S. Shushpannikova ◽  
L. P. Turubanova
Keyword(s):  
Komi Republic ◽  
Oil Fields ◽  
Soil Enrichment ◽  
Far North ◽  
North East ◽  
European North ◽  
Ecological Scales ◽  
Floristic Classification ◽  
Made In

The results of floristic classification of technogenic vegetation (alliance Chamerio angustifolii–Matricarion hookeri A. Ishbirdin et al. 1996, order Chamerio–Betuletalia nanae Khusainov et al. in Sumina 2012, class Matricario–Poetea arcticae A. Ishbirdin in Sumina 2012) conducted by the Braun-Blanquet method (Braun-Blanquet, 1964; Mirkin, Naumova, 1998) are given. 98 geobotanical relevés, made in 1981–2013 on areas of oil fields and suburbs of the Usinsk city (Komi Republic) (56–60о N, 67–66о E), were involved into analysis (Fig. 1). The ecological parameters like moisture (F) and mineral nitrogen soil enrichment (N) were assessed using the Ellenberg ecological scales (Ellenberg, 1974).

Imaging of Bacteria: Is there Any Hope for the Future Based on Past Experience?

2018 ◽  
Vol 24 (7) ◽  
pp. 772-786 ◽  
Author(s):  
Thomas Ebenhan ◽  
Elena Lazzeri ◽  
Olivier Gheysens
Keyword(s):  
Clinical Practice ◽  
Sterile Inflammation ◽  
Ageing Population ◽  
Major Health Problem ◽  
Major Health ◽  
Number Of Patients ◽  
Implanted Medical Devices ◽  
Neutropenic Patients ◽  
Socio Economic Impact ◽  
Made In

Infectious diseases remain a major health problem and cause of death worldwide. It is expected that the socio-economic impact will further intensify due to escalating resistance to antibiotics, an ageing population and an increase in the number of patients under immunosuppressive therapy and implanted medical devices. Even though radiolabeled probes and leukocytes are routinely used in clinical practice, it might still be difficult to distinguish sterile inflammation from inflammation caused by bacteria. Moreover, the majority of these probes are based on the attraction of leukocytes which may be hampered in neutropenic patients. Novel approaches that can be implemented in clinical practice and allow for swift diagnosis of infection by targeting the microorganism directly, are posing an attractive strategy. Here we review the current strategies to directly image bacteria using radionuclides and we provide an overview of the preclinical efforts to develop and validate new approaches. Indeed, significant progress has been made in the past years, but very few radiopharmaceuticals (that were promising in preclinical studies) have made it into clinical practice. We will discuss the challenges that remain to select good candidates for imaging agents targeting bacteria.

Sign in / Sign up

Export Citation Format

Share Document